AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Robust Adaptation of Foundation Models With Black-Box Visual Prompting

Changdae Oh, Gyeongdeok Seo, Geunyoung Jung, Zhi-Qi Cheng, Hosik Choi, Jiyoung Jung, Kyungwoo Song

TPAMI 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Robustness benchmarks and defenses · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add input-dependent Coordinator prompts (BlackVIP) over VP w/ SPSA-GC (ablation)VP w/ SPSA-GC · Biased MNIST (rho=0.8)accuracy (%): 60.34 -> 66.21Improved
add input-dependent Coordinator prompts (BlackVIP) over VP w/ SPSA-GC (ablation)VP w/ SPSA-GC · Loc-MNIST (1:1)accuracy (%): 16.21 -> 69.08Improved
add input-dependent Coordinator prompts (BlackVIP) over VP w/ SPSA-GC (ablation)VP w/ SPSA-GC · 14 few-shot benchmarksavg accuracy (%): 58.8 -> 64.0Improved
add black-box prompting (BlackVIP) over zero-shot (ablation)CLIP ViT-B/16 · 14 few-shot benchmarksavg accuracy (%): 57.6 -> 64.0Improved
replace pretrained SSL encoder with PCA features (BlackVIP-SE) (ablation)BlackVIP · 14 few-shot benchmarksavg accuracy (%): 64.0 -> 63.5No clear effect
replace pretrained SSL encoder with PCA features (BlackVIP-SE) (ablation)BlackVIP · Biased MNIST (rho=0.8)accuracy (%): 66.21 -> 55.73Hurt
replace pretrained SSL encoder with PCA features (BlackVIP-SE) (ablation)BlackVIP · ImageNet-1K train-time peak memory (ViT-B)peak memory (MB): 2,428 -> 1,319Improved
replace pretrained SSL encoder with PCA features (BlackVIP-SE) (ablation)BlackVIP · training runtime per batchseconds: 0.2684 -> 0.1233Improved
add BlackVIP visual prompt to CuPL text prompt (ablation)CuPL · EuroSATaccuracy (%): 45.91 -> 68.88Improved
add BlackVIP visual prompt to LLM BBO text prompt (ablation)LLM BBO · EuroSATaccuracy (%): 52.80 -> 71.80Improved
add BlackVIP visual prompt to CuPL text prompt (ablation)CuPL · DTDaccuracy (%): 55.85 -> 55.58No clear effect
increase Coordinator parameters from 9K to 150K in white-box regime (ablation)Ours · SVHN/CLEVR/Pets averageavg accuracy (%): 64.6 -> 66.1Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy